Accurate segmentation of sub-cortical brain regions (the deep nuclei - caudate, putamen, ventral striatum, thalamus, hippocampus, amygdala) from high resolution MR data such as 3D T1-weighted sequences (e.g. Siemens MPRAGE, GE FSPGR) is a requirement in the study of diseases such as Parkinson’s using imaging. The segmented VOIs may be used for volumetric analysis of MRI data in the input image space or also for PET/SPECT quantification. Traditional methods of achieving this through spatial normalization to brain templates can fail or be inaccurate in some cases, particularly when there is pronounced brain atrophy. PMOD’s PNEURO Parcellation workflow is specifically designed to provide increased accuracy for deep nuclei segmentation but requires additional processing time compared to template-based normalization and can still struggle in cases with severe atrophy.
We hypothesized that AI-based segmentation could be used as an alternative for cases with severe atrophy or where traditional methods struggled.
To test this hypothesis we used data from the IXI database of 3D T1-weighted MR:
https://brain-development.org/ixi-dataset/
Example data to test the IXI Parcellation model is available in our Demo database (Subject PAI4). The data used for the case study was extracted from the IXI dataset: https://brain-development.org/ixi-dataset/
To try the model for yourself we recommend use of the Segment tool (PSEG). The PAI4 example has the required orientation and any new data used for testing should match this. Cropping is not strictly required but is recommended to reduce the field-of-view to the brain. The model selection is IXI Parcellation (Multichannel Segmentation). The model was trained with 3D data so Split Slices/Frames is not available/required. The data used in these cases was all T1-weighted 3D MR - the performance of the model may vary for data from different hardware and/or with different contrast/pre-processing.